|
| 1 | +.. _apicomm: |
| 2 | + |
| 3 | +flashinfer.comm |
| 4 | +=============== |
| 5 | + |
| 6 | +.. currentmodule:: flashinfer.comm |
| 7 | + |
| 8 | +This module provides communication primitives and utilities for distributed computing, including CUDA IPC, AllReduce operations, and memory management utilities. |
| 9 | + |
| 10 | +CUDA IPC Utilities |
| 11 | +------------------ |
| 12 | + |
| 13 | +.. autosummary:: |
| 14 | + :toctree: ../generated |
| 15 | + |
| 16 | + CudaRTLibrary |
| 17 | + create_shared_buffer |
| 18 | + free_shared_buffer |
| 19 | + |
| 20 | +DLPack Utilities |
| 21 | +---------------- |
| 22 | + |
| 23 | +.. autosummary:: |
| 24 | + :toctree: ../generated |
| 25 | + |
| 26 | + pack_strided_memory |
| 27 | + |
| 28 | +Mapping Utilities |
| 29 | +----------------- |
| 30 | + |
| 31 | +.. autosummary:: |
| 32 | + :toctree: ../generated |
| 33 | + |
| 34 | + Mapping |
| 35 | + |
| 36 | +TensorRT-LLM AllReduce |
| 37 | +---------------------- |
| 38 | + |
| 39 | +Types and Enums |
| 40 | +~~~~~~~~~~~~~~~~ |
| 41 | + |
| 42 | +.. autosummary:: |
| 43 | + :toctree: ../generated |
| 44 | + |
| 45 | + AllReduceFusionOp |
| 46 | + AllReduceFusionPattern |
| 47 | + AllReduceStrategyConfig |
| 48 | + AllReduceStrategyType |
| 49 | + FP4QuantizationSFLayout |
| 50 | + |
| 51 | +Core Operations |
| 52 | +~~~~~~~~~~~~~~~ |
| 53 | + |
| 54 | +.. autosummary:: |
| 55 | + :toctree: ../generated |
| 56 | + |
| 57 | + trtllm_allreduce_fusion |
| 58 | + trtllm_custom_all_reduce |
| 59 | + trtllm_moe_allreduce_fusion |
| 60 | + trtllm_moe_finalize_allreduce_fusion |
| 61 | + |
| 62 | +Workspace Management |
| 63 | +~~~~~~~~~~~~~~~~~~~~ |
| 64 | + |
| 65 | +.. autosummary:: |
| 66 | + :toctree: ../generated |
| 67 | + |
| 68 | + trtllm_create_ipc_workspace_for_all_reduce |
| 69 | + trtllm_create_ipc_workspace_for_all_reduce_fusion |
| 70 | + trtllm_destroy_ipc_workspace_for_all_reduce |
| 71 | + trtllm_destroy_ipc_workspace_for_all_reduce_fusion |
| 72 | + |
| 73 | +Initialization and Utilities |
| 74 | +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ |
| 75 | + |
| 76 | +.. autosummary:: |
| 77 | + :toctree: ../generated |
| 78 | + |
| 79 | + trtllm_lamport_initialize |
| 80 | + trtllm_lamport_initialize_all |
| 81 | + compute_fp4_swizzled_layout_sf_size |
| 82 | + |
| 83 | +vLLM AllReduce |
| 84 | +-------------- |
| 85 | + |
| 86 | +.. autosummary:: |
| 87 | + :toctree: ../generated |
| 88 | + |
| 89 | + vllm_all_reduce |
| 90 | + vllm_dispose |
| 91 | + vllm_init_custom_ar |
| 92 | + vllm_register_buffer |
| 93 | + vllm_register_graph_buffers |
| 94 | + vllm_get_graph_buffer_ipc_meta |
| 95 | + vllm_meta_size |
| 96 | + |
| 97 | +MNNVL (Multi-Node NVLink) |
| 98 | +------------------------- |
| 99 | + |
| 100 | +.. currentmodule:: flashinfer.comm.mnnvl |
| 101 | + |
| 102 | +Core Classes |
| 103 | +~~~~~~~~~~~~ |
| 104 | + |
| 105 | +.. autosummary:: |
| 106 | + :toctree: ../generated |
| 107 | + |
| 108 | + MnnvlMemory |
| 109 | + McastGPUBuffer |
| 110 | + |
| 111 | +Utility Functions |
| 112 | +~~~~~~~~~~~~~~~~~ |
| 113 | + |
| 114 | +.. autosummary:: |
| 115 | + :toctree: ../generated |
| 116 | + |
| 117 | + create_tensor_from_cuda_memory |
| 118 | + alloc_and_copy_to_cuda |
| 119 | + |
| 120 | +TensorRT-LLM MNNVL AllReduce |
| 121 | +---------------------------- |
| 122 | + |
| 123 | +.. currentmodule:: flashinfer.comm.trtllm_mnnvl_ar |
| 124 | + |
| 125 | +.. autosummary:: |
| 126 | + :toctree: ../generated |
| 127 | + |
| 128 | + trtllm_mnnvl_all_reduce |
| 129 | + trtllm_mnnvl_fused_allreduce_rmsnorm |
| 130 | + mpi_barrier |
0 commit comments